Dual-Locking Learned AI Models: A PIN-Based Sparse QIM Watermarking and Adaptive Index Permutation Approach

Iva Vasic, Jesús Muñoz-Cádiz, Bata Vasic

We present a dual-locking method for securing trained neural networks that combines key-driven index permutation with PIN-based watermarking based on Sparse Quantization Index Modu…